INDEX

Explanations

mentions of the word "Avatar"

oai_token-act-pair · gpt-3.5-turbo

references to the video game "Atari" and related franchises

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

esters

-0.85

ortun

-0.81

giving

-0.70

mington

-0.69

stab

-0.67

uter

-0.67

 Dodd

-0.67

ec

-0.66

found

-0.66

cker

-0.66

POSITIVE LOGITS

 Korra

1.06

atar

1.03

atars

0.91

 Roku

0.86

idon

0.86

 Avatar

0.83

âĹ¼

0.81

DragonMagazine

0.78

inho

0.76

abal

0.76

Activations Density 0.029%

mentions of the word "Avatar"

references to the video game "Atari" and related franchises

No Comments

No Known Activations